chauhoang commited on
Commit
947dd3b
·
verified ·
1 Parent(s): af52c1f

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a34d0cc9dce069f0438b4a60020412ebe7c0684696a984560953cba3f53518f1
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3076c9e4b22ccda1d157440309438592bd72e05f4fcb3b12d5ab6457c5abb65
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ad7057154808fa2d130ca33f6536a82b5e51516346a21d84033936c69f498e9
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1d1a459d78a0be1cdb36430c753a112c19893ee10cfe16d8aa3e8fe1062728
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44080f4551542643a1250aa7407fe87ae5ca6d5a97f61f4ec4a60a7057ff55ca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a1f3155b537276c540b4b359f6f1735227a9b243af29aedc24435ca462f4e6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0010958326747800432,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 3.4654,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8938615908335616.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0016437490121700648,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 3.4654,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001264422317053896,
72
+ "grad_norm": 3.261793613433838,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.3791,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001264422317053896,
79
+ "eval_loss": 0.8699796199798584,
80
+ "eval_runtime": 1150.77,
81
+ "eval_samples_per_second": 8.681,
82
+ "eval_steps_per_second": 4.341,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001475159369896212,
87
+ "grad_norm": 3.957169771194458,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.5432,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3407923862503424e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null